INDEX

Explanations

scientific terminology and structured data references

oai_token-act-pair · gpt-4o-mini Triggered by @bot

treated rabbitcoronary arteryF orientation

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-0.58

 argint

-0.52

 dezelve

-0.51

 contemporanea

-0.50

umoj

-0.50

 plufieurs

-0.49

tamia

-0.49

 müſſen

-0.49

pingente

-0.49

 hunne

-0.49

POSITIVE LOGITS

 ""],

0.52

-------------</

0.43

BnF

0.41

<",

0.40

imageshack

0.37

__':

0.35

Legături

0.34

InjectAttribute

0.34

#+#

0.33

=$?

0.33

Activations Density 0.337%

scientific terminology and structured data references

treated rabbitcoronary arteryF orientation

No Comments

No Known Activations